Beheading-Block&Axe-LoRA-V1 for SD1.5

The LoRA model as an extension for Stable Diffusion 1.5

The LoRA allows scenes of execution by decapitation with block and axe. Typically, the victim kneels in front of a block of wood and the executioner cuts off the head with an axe.

It is designed to create classic medieval or fantasy scenes with the typical executioners with or without hoods, axes and wooden blocks. It works with both men and women as victims.

It can of course be influenced, swords as execution elements have also appeared in testing and standing is also possible etc. but that then requires more creative prompting and possibly negative prompts etc.

It can also be added blood, and scenes before, during and after the execution are possible.

It was trained with about 1200 images and 38 tags and can be used with many styles.

Of course you need Stable Diffusion 1.5 or a checkpoint based on the 1.5 model and one of the many user interfaces to use it.

There are 6 different LoRA models included in the archive, which have been trained at different levels. It always depends on the scene, models used, trigger words, etc. which LoRA is most suitable. So you can try and choose for yourself.

In addition, 36 images are included as an example in PNG format and with the complete generation data.

Don't expect perfect pictures from the LoRA, it depends a lot on the combination of different checkpoints, LoRAs and prompts how good the pictures will be. It will be very rare to create an image that does not require a little post-processing, e.g. inpainting. The promo images give a small impression, but of course they are a selection of the best images and a lot of images have been sorted out.

All product images are unedited (only ADetailer was used in most images for the automatic enhancement of faces) and were created with various 1.5 checkpoints and LoRAs with Automatic1111